© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3156
    Prev
    Next
    INDEX
    Explanations

    code snippets

    oai_token-act-pair · gemini-2.0-flash

    Code and memory regions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TagMode
    -0.89
    windowFixed
    -0.72
    fromnode
    -0.72
    SourceChecksum
    -0.69
     cherchés
    -0.69
    Chham
    -0.68
    CompilerServices
    -0.66
     estekak
    -0.66
    Portail
    -0.65
    TabIndex
    -0.65
    POSITIVE LOGITS
     réessayer
    0.42
    olid
    0.39
    oplast
    0.39
    providedIn
    0.38
    nesc
    0.35
    Us
    0.35
    ModelBuilder
    0.34
    op
    0.33
    iglie
    0.33
     Last
    0.32
    Activations Density 9.487%

    No Known Activations